OmniHuman 2.0 Audio to Video

curl --request POST \
  --url https://api.vidgo.ai/api/generate/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "bytedance/omnihuman-2.0/audio-to-video",
  "input": {
    "image_urls": [
      "https://example.com/presenter.png"
    ],
    "audio_url": "https://example.com/voiceover.mp3"
  }
}
'

{
  "code": 200,
  "data": {
    "task_id": "task-unified-1762160000-abc123",
    "status": "not_started",
    "created_time": "2026-11-03T10:30:00"
  }
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

Request timeout

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

POST

api

generate

submit

curl --request POST \
  --url https://api.vidgo.ai/api/generate/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "bytedance/omnihuman-2.0/audio-to-video",
  "input": {
    "image_urls": [
      "https://example.com/presenter.png"
    ],
    "audio_url": "https://example.com/voiceover.mp3"
  }
}
'

{
  "code": 200,
  "data": {
    "task_id": "task-unified-1762160000-abc123",
    "status": "not_started",
    "created_time": "2026-11-03T10:30:00"
  }
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

Request timeout

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

After submission, a task_id will be returned. If you provided a callback_url, when the task status becomes finished or failed, a POST request will be sent to the callback_url.
Regardless of whether callback_url is provided, you can retrieve the result through the unified Query Task Status endpoint.

OmniHuman 2.0 Audio to Video takes one character image and one audio file and generates a 720p video of that character speaking, singing or performing, with lip movement, expression and gestures following the audio. It accepts 4–300 seconds of audio, so it works for short social clips as well as full explainer narrations. OmniHuman 2.0 is ByteDance’s audio-driven video model, offered upstream through BytePlus.

Models

bytedance/omnihuman-2.0/audio-to-video — Audio-to-video with OmniHuman 2.0: one image plus one WAV or MP3 file, 720p output, length follows the audio.

Features

Audio-driven talking and singing videos from a single image.
Lip sync, expression and gestures driven by the audio.
Audio from 4 seconds up to 5 minutes; the video is as long as the audio.
Works with people, animals, cartoon, 3D and stylized characters, and multi-person images.
Optional prompt for camera movement, actions and added scene elements.

Required parameters

image_urls (string[]): Exactly one public HTTP(S) image URL of the character. The framing of the video follows this image.
audio_url (string): Public HTTP(S) URL of a WAV or MP3 file, at most 15 MB and 4–300 seconds long.

Optional parameters

prompt (string): Camera movement, actions or extra scene elements. Lip movement and expression still come from the audio.

Duration

There is no duration field. The output length follows the audio, so a 30-second voice-over gives a video of about 30 seconds. Trim the audio to change the length.

Output

The finished task returns one MP4 video in the files array of Query Task Status and the callback payload. The video is 720p.

Examples

Talking presenter from a headshot: one headshot and an MP3 voice-over, no prompt.
Singing character with a camera prompt and callback: a cartoon cat, a WAV song, a prompt for movement and camera, and a callback_url.

Notes

Use one clear image with a visible face and clean audio without long silences or heavy background noise for the most accurate lip sync.
Audio that is not WAV or MP3, larger than 15 MB, shorter than 4 seconds or longer than 300 seconds returns 400. duration, resolution, aspect_ratio, seed and any other field not listed above also return 400.
model and callback_url belong at the request root, not inside input.
Credits are billed per second of generated video. At submission, credits for the full audio length are reserved. When the task succeeds, the charge is settled on the actual output length and any difference is refunded; the final charge never exceeds the reserved amount. A failed task is refunded in full. See the pricing page for current rates.

Authorizations

Authorization

string

header

required

All API endpoints require Bearer Token authentication

Get your API Key:

Go to Dashboard → API Key (API Key Management Page) to get your API Key

Add it to the request header:

Authorization: Bearer VIDGO_API_KEY

Body

application/json

model

string

required

Model ID. Use bytedance/omnihuman-2.0/audio-to-video.

Example:

"bytedance/omnihuman-2.0/audio-to-video"

input

object

required

Generation parameters.

Show child attributes

callback_url

string<uri> | null

Optional public HTTP(S) endpoint that receives a POST when the task becomes finished or failed. HTTPS is recommended. Omit it, or send null or an empty string, to disable callbacks.

Example:

"https://your-domain.com/callback"

Response

Task submitted

code

enum<integer>

required

HTTP status code.

Available options:

200

data

object

required

Show child attributes

​Models

​Features

​Required parameters

​Optional parameters

​Duration

​Output

​Examples

​Notes

Authorizations

Body

Response

Models

Features

Required parameters

Optional parameters

Duration

Output

Examples

Notes